Pixel-level Road Crack Detection and Segmentation Based on Deep Learning
|
|
|||||||||||
Bibliografische Angaben
| Autor(en): |
Lu Deng
(Hunan University, Changsha, Hunan, China; Hunan Key Laboratory of Damage Diagnosis of Engineering Structures, Changsha, Hunan, China)
An Zhang (Hunan University, Changsha, Hunan, China; Hunan Key Laboratory of Damage Diagnosis of Engineering Structures, Changsha, Hunan, China) Ran Cao (Hunan University, Changsha, Hunan, China; Hunan Key Laboratory of Damage Diagnosis of Engineering Structures, Changsha, Hunan, China) |
||||
|---|---|---|---|---|---|
| Medium: | Tagungsbeitrag | ||||
| Sprache(n): | Englisch | ||||
| Tagung: | IABSE Congress: Bridges and Structures: Connection, Integration and Harmonisation, Nanjing, People's Republic of China, 21-23 September 2022 | ||||
| Veröffentlicht in: | IABSE Congress Nanjing 2022 | ||||
|
|||||
| Seite(n): | 1346-1352 | ||||
| Anzahl der Seiten (im PDF): | 7 | ||||
| DOI: | 10.2749/nanjing.2022.1346 | ||||
| Abstrakt: |
This paper proposed an integrated framework for detecting and segmenting road cracks in complex backgrounds. Based on the latest real-time object detection algorithm, YOLOv5l6, a modified U-Net embedded Bottleneck and Attention mechanism modules was developed to segment crack pixels from the detected crack regions. Validation of the proposed approach was conducted based on a total of 150 images, which were taken from different backgrounds, angles, and distances. Based on the computation, the results derived from the YOLOv5l6-based crack detection had a mean average precision of 92%, and the mean intersection of the union of the modified U-Net was 87%, which is at least 11% higher than the original U-Net model. The results showed the integrated approach could be a potential basis for an automated road-condition evaluation scheme for road operation and maintenance. |
||||
| Copyright: | © 2022 International Association for Bridge and Structural Engineering (IABSE) | ||||
| Lizenz: | Die Urheberrechte (Copyright) für dieses Werk sind rechtlich geschützt. Es darf nicht ohne die Zustimmung des Autors/der Autorin oder Rechteinhabers/-in weiter benutzt werden. |
||||